Session Ready
Exercise

Transforming the response variable too

The response variable can be transformed too, but this means you need an extra step at the end to undo that transformation. That is, you "back transform" the predictions.

In the video, you saw the first step of the digital advertising workflow: spending money to buy ads, and counting how many people see them (the "impressions"). The next step is determining how many people click on the advert after seeing it.

ad_conversion is available as a pandas DataFrame.

Instructions 1/3
undefined XP
  • 1
  • 2
  • 3
  • Look at the plot.
  • Create a qdrt_n_impressions column using n_impressions raised to the power of 0.25.
  • Create a qdrt_n_clicks column using n_clicks raised to the power of 0.25.
  • Create a regression plot using the transformed variables. Do the points track the line more closely?